other · Underline Science Inc. · 2023

Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling

Association for Computational Linguistics 2023, Ko, Youngjoong, You, Jaeah

Cited by 0Open access

Abstract

Dealing with multiple topics should be considered an important issue in dialogue summarization, because dialogues, unlike documents, are prone to topic drift. Thus, we propose a new dialogue summarization model that reflects dialogue topic distribution to consider all topics present in the dialogue. First, the distribution of dialogue topics is estimated by an effective topic discovery model. Then topic-informed prompt transfers estimated topic distribution information to the output of encoder and decoder vectors. Finally, the topic extractor estimates the summary topic distribution from the output context vector of decoder to distinguish its difference from the dialogue topic distribution. To consider the proportion of each topic distribution appeared in the dialogue, the extractor is trained to reduce the difference between the distributions of the dialogue and the summary. The experimental results on SAMSum and DialogSum show that our model outperforms state-of-the-art methods on ROUGE scores. The human evaluation results also show that our framework well generates comprehensive summaries.

Cite this paper

APA 7

2023, A. F. C. L., Ko, Y., & You, J. (2023). Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling. Underline Science Inc.. https://doi.org/10.48448/e8qn-z043

MLA 9

2023, Association for Computational Linguistics, et al. “Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling.” Underline Science Inc., 2023, https://doi.org/10.48448/e8qn-z043.

Chicago

2023, Association for Computational Linguistics, Youngjoong Ko, and Jaeah You. 2023. “Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling.” Underline Science Inc.. https://doi.org/10.48448/e8qn-z043.

Harvard

2023, A.F.C.L., Ko, Y. and You, J. (2023) ‘Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling’, Underline Science Inc.. Available at: https://doi.org/10.48448/e8qn-z043.

BibTeX

@misc{20232023topic,
  title = {{Topic-Informed Dialogue Summarization using Topic Distribution and Prompt-based Modeling}},
  author = {2023, Association for Computational Linguistics and Ko, Youngjoong and You, Jaeah},
  journal = {Underline Science Inc.},
  year = {2023},
  doi = {10.48448/e8qn-z043}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.